Tag
This paper reframes conformance for use-based AI regulation as a failure rate under a declared distribution of contexts, studying delegation contracts under strategic interaction among deployers, auditors, and enforcement points. It proposes mechanisms including proper-scoring penalties, commit-reveal audits, alpha-investing error budgets, and subgroup guarantees, contrasting conformance-as-a-rate with the EU AI Act's static conformity assessment.
This paper studies whether interaction formats (like sequential/ascending auction interfaces) and textual reasoning scaffolds improve how LLM agents make strategic decisions in auctions and matching environments. It finds that simpler interfaces and payoff-contingency prompts reduce bid deviations, but these behavioral gains do not necessarily show up in the agents' stated explanations—suggesting scaffolds should be evaluated by realized choices, not just verbal indicators.
The paper reformulates AI alignment as a social choice problem using linear optimization over a convex impact space, applying welfare economics and mechanism design to derive alignment protocols. It empirically illustrates welfare implications using real human preferences in scenarios like kidney allocation and trolley problems.
Princeton University announces its Spring 2025 course on Economics and Computation, taught by Matt Weinberg and Mark Braverman, covering topics like game theory, auctions, mechanism design, and cryptocurrencies.
This paper presents a mechanism-design framework for verifying negotiation and allocation tasks in LLM agents using A2A/MCP protocols. It evaluates rational behavior across models, finding that mechanism-level incentive compatibility does not automatically transfer to LLM agents.
This paper models the strategic interaction between content providers and generative search engines as a repeated Stackelberg game, showing how GEO can escalate into citation wars, and proposes a verifiable-content reward mechanism (VCR) to align incentives and achieve win-win outcomes.
This paper formalizes agent coalition formation and inter-agent communication as a cooperative game, proposing marginal-value activation rules and Shapley-based online routing to reduce token costs and improve efficiency in multi-agent LLM systems, with theoretical guarantees and synthetic simulation results.
This paper introduces LLM-OSDA, a dynamic cost-per-click auction for native advertising in multi-turn LLM conversations, integrating Bellman optimal stopping, winner allocation, and envelope pricing. Experiments show an 11% net revenue improvement over fixed-timing baselines while maintaining user retention.
This paper investigates formal mechanisms, such as Mediation, to maintain market stability among self-interested LLM agents (DeepSeek-V3) in a simulated marketplace, finding that Mediation enables recovery even under sustained adversarial attacks.
This paper proposes Representation Curriculum (RC), a training-time intervention that stages feature utilization to reduce over-reliance on exposure-confounded historical signals and improve cold-start generalization in ranking systems. The method is theoretically analyzed and validated on public benchmarks and large-scale eBay search experiments.
This paper reformulates hospital mechanism design as program synthesis for language models, using a multi-agent simulator (Medi-Sim) to evaluate policy rules under strategic provider responses. It demonstrates pressure migration across provider channels and synthesizes an inspectable mixed-objective program that reduces up-coding and rejection while retaining funds.
This paper proposes a game-theoretic framework to address AI-induced delusional belief spirals caused by sycophantic chatbots. It introduces 'Belief Versioning,' an inference-time intervention that reduces spiral rates significantly in simulations and GPT-4o tests.
OpenSimula, an open-source Python implementation of the Simula mechanism-design recipe for controlled synthetic-data generation, has been added to the AfterImage dataset tool.